Explore the vast range of titles available.

Symbolic regression is emerging as a promising machine learning method for learning succinct underlying interpretable mathematical expressions directly from data. Whereas it has been traditionally tackled with genetic programming, it has recently gained a growing interest in deep learning as a data-driven model discovery tool, achieving significant advances in various application domains ranging from fundamental to applied sciences. In this survey, we present a structured and comprehensive overview of symbolic regression methods, review the adoption of these methods for model discovery in various areas, and assess their effectiveness. We have also grouped state-of-the-art symbolic regression applications in a categorized manner in a living review.

Machine learning is rapidly making its path into the natural sciences, including high-energy physics. We present the first study that infers, directly from experimental data, a functional form of fragmentation functions. The latter represent a key ingredient to describe physical observables measured in high-energy physics processes that involve hadron production, and predict their values at different energies. Fragmentation functions cannot be calculated in theory and have to be determined instead from data. Traditional approaches rely on global fits of experimental data to learn the parameters of a pre-assumed functional form inspired from phenomenological models of hadron production. This novel approach uses an ML technique, namely symbolic regression (SR), to learn an analytical model from measured charged hadron multiplicities. The function studied by SR resembles the Lund string function and describes the data well, thus representing a potential candidate for use in global FFs fits.

In neonatal encephalopathy, the clinical manifestations of injury can only be reliably assessed several years after an intervention, complicating early prognostication and rendering trials of promising neuroprotectants slow and expensive. We aimed to determine the accuracy of thalamic proton magnetic resonance (MR) spectroscopy (MRS) biomarkers as early predictors of the neurodevelopmental abnormalities observed years after neonatal encephalopathy. We did a prospective multicentre cohort study across eight neonatal intensive care units in the UK and USA, recruiting term and near-term neonates who received therapeutic hypothermia for neonatal encephalopathy. We excluded infants with life-threatening congenital malformations, syndromic disorders, neurometabolic diseases, or any alternative diagnoses for encephalopathy that were apparent within 6 h of birth. We obtained T1-weighted, T2-weighted, and diffusion-weighted MRI and thalamic proton MRS 4–14 days after birth. Clinical neurodevelopmental tests were done 18–24 months later. The primary outcome was the association between MR biomarkers and an adverse neurodevelopmental outcome, defined as death or moderate or severe disability, measured using a multivariable prognostic model. We used receiver operating characteristic (ROC) curves to examine the prognostic accuracy of the individual biomarkers. This trial is registered with ClinicalTrials.gov, number NCT01309711. Between Jan 29, 2013, and June 25, 2016, we recruited 223 infants who all underwent MRI and MRS at a median age of 7 days (IQR 5–10), with 190 (85%) followed up for neurological examination at a median age of 23 months (20–25). Of those followed up, 31 (16%) had moderate or severe disability, including one death. Multiple logistic regression analysis could not be done because thalamic N-acetylaspartate (NAA) concentration alone accurately predicted an adverse neurodevelopmental outcome (area under the curve [AUC] of 0·99 [95% CI 0·94–1·00]; sensitivity 100% [74–100]; specificity 97% [90–100]; n=82); the models would not converge when any additional variable was examined. The AUC (95% CI) of clinical examination at 6 h (n=190) and at discharge (n=167) were 0·72 (0·65–0·78) and 0·60 (0·53–0·68), respectively, and the AUC of abnormal amplitude integrated EEG at 6 h (n=169) was 0·73 (0·65–0·79). On conventional MRI (n=190), cortical injury had an AUC of 0·67 (0·60–0·73), basal ganglia or thalamic injury had an AUC of 0·81 (0·75–0·87), and abnormal signal in the posterior limb of internal capsule (PLIC) had an AUC of 0·82 (0·76–0·87). Fractional anisotropy of PLIC (n=65) had an AUC of 0·82 (0·76–0·87). MRS metabolite peak-area ratios (n=160) of NAA–creatine (<1·29) had an AUC of 0·79 (0·72–0·85), of NAA–choline had an AUC of 0·74 (0·66–0·80), and of lactate–NAA (>0·22) had an AUC of 0·94 (0·89–0·97). Thalamic proton MRS measures acquired soon after birth in neonatal encephalopathy had the highest accuracy to predict neurdevelopment 2 years later. These methods could be applied to increase the power of neuroprotection trials while reducing their duration. National Institute for Health Research UK.

Perovskites have stood out as excellent photoactive materials with high efficiencies and stabilities, achieved via cation mixing techniques. Overcoming challenges to the stabilization of Perovskite solar cells calls for the development of design principles of large cation incorporation in halide perovskite to accelerate the discovery of optimal stable compositions. Large fluorinated organic cations incorporation is an attractive method for enhancing the intrinsic stability of halide perovskites due to their high dipole moment and moisture-resistant nature. However, a fluorinated cation has a larger ionic size than its non-fluorinated counterpart, falling within the upper boundary of the mixed-cation incorporation. Here, we report on the intrinsic stability of mixed Methylammonium (MA) lead halides at different concentrations of large cation incorporation, namely, ehtylammonium (EA; [CH3CH2NH3]+) and 2-fluoroethylammonium (FEA; [CH2FCH2NH3]+). Density functional theory (DFT) calculations of the enthalpy of the mixing and analysis of the perovskite structural features enable us to narrow down the compositional search domain for EA and FEA cations around concentrations that preserve the perovskite structure while pointing towards the maximal stability. This work paves the way to developing design principles of a large cation mixture guided by data analysis of DFT data. Finally, we present the automated search of the minimum enthalpy of mixing by implementing Bayesian optimization over the compositional search domain. We introduce and validate an automated workflow designed to accelerate the compositional search, enabling researchers to cut down the computational expense and bias to search for optimal compositions.

Recommender systems are widely used in online platforms for easy exploration of personalized content. The best available recommendation algorithms are based on using the observed preference information among collaborating entities. A significant challenge in recommender system continues to be item cold-start recommendation: how to effectively recommend items with no observed or past preference information. Here we propose a two-stage algorithm based on soft clustering to provide an efficient solution to this problem. The crux of our approach lies in representing the items as soft-cluster embeddings in the space spanned by the side-information associated with the items. Though many item embedding approaches have been proposed for item cold-start recommendations in the past—and simple as they might appear—to the best of our knowledge, the approach based on soft-cluster embeddings has not been proposed in the research literature. Our experimental results on four benchmark datasets conclusively demonstrate that the proposed algorithm makes accurate recommendations in item cold-start settings compared to the state-of-the-art algorithms according to commonly used ranking metrics like Normalized Discounted Cumulative Gain (NDCG) and Mean Average Precision (MAP). The performance of our proposed algorithm on the MovieLens 20M dataset clearly demonstrates the scalability aspect of our algorithm compared to other popular algorithms. We also propose the metric Cold Items Precision (CIP) to quantify the ability of a system to recommend cold-start items. CIP can be used in conjunction with relevance ranking metrics like NDCG and MAP to measure the effectiveness of the cold-start recommendation algorithm.

Background The COVID-19 pandemic has strained healthcare systems by creating a tragic imbalance between needs and resources. Governments and healthcare organizations have adapted to this pronounced scarcity by applying allocation guidelines to facilitate life-or-death decision-making, reduce bias, and save as many lives as possible. However, we argue that in societies beset by longstanding inequities, these approaches fall short as mortality patterns for historically discriminated against communities have been disturbingly higher than in the general population. Methods We review attack and fatality rates; survey allocation protocols designed to deal with the extreme scarcity characteristic of the earliest phases of the pandemic; and highlight the larger ethical perspectives (Utilitarianism, non-Utilitarian Rawlsian justice) that might justify such allocation practices. Results The COVID-19 pandemic has dramatically amplified the dire effects of disparities with respect to the social determinants of health. Patients in historically marginalized groups not only have significantly poorer health prospects but also lower prospects of accessing high quality medical care and benefitting from it even when available. Thus, mortality among minority groups has ranged from 1.9 to 2.4 times greater than the rest of the population. Standard allocation schemas, that prioritize those most likely to benefit, perpetuate and may even exacerbate preexisting systemic injustices. Conclusions To be better prepared for the inevitable next pandemic, we must urgently begin the monumental project of addressing and reforming the structural inequities in US society that account for the strikingly disparate mortality rates we have witnessed over the course of the current pandemic.

Background Bronchopulmonary dysplasia (BPD) affects up to half of extremely preterm infants, and is associated with adverse long-term respiratory, neurodevelopmental, and educational sequelae and costly health service and family economic outcomes. The NICHD Neonatal Research Network Hydrocortisone for Bronchopulmonary Dysplasia (BPD) Trial evaluated the efficacy and safety of hydrocortisone treatment to prevent BPD in high-risk infants. The trial enrolled 800 very preterm infants with respiratory failure and followed the participants until 2 years corrected age to assess safety of the trial intervention. Longer-term impacts of hydrocortisone exposure and severity of BPD on functional outcomes of high-risk infants remain unknown. The HYdrocortisone for BPD Respiratory and Developmental (HYBRiD) Outcomes Study extends follow-up of all surviving children enrolled in the Hydrocortisone for BPD Trial until early school age. It aims to characterize the childhood functional motor, cognitive, academic, and pulmonary outcomes of this large, well-phenotyped trial cohort. Methods Parents of surviving trial participants complete telephone questionnaires when their children are 3 and 4 years corrected age. A single in-person study visit takes place at early school age (5 years, 0 months to 7 years, 11 months corrected age). Children undergo a multidimensional assessment of functional outcomes and parents complete a battery of questionnaires. In 5 of 19 participating centers, respiratory mechanics are evaluated with impulse oscillometry. Discussion The HYBRiD Outcomes Study will be the largest and most comprehensive evaluation to date of the functional early school age outcomes of children with a history of severe neonatal lung disease and of children exposed to HC during infancy. This will substantially improve understanding of the longer-term implications of severe neonatal lung disease; provide data to facilitate the development of future randomized intervention trials in this population; and inform public policy by enhancing knowledge about school age resource requirements in children with a history of prematurity and lung disease. Trial registration clinicaltrials.gov ID NCT01353313. Primary trial registration 5/11/11 modified to include followup through school age 12/13/17. This manuscript reflects version 3 of the trial manuscript, dated 10/12/2020.

ObjectiveEvaluate if odds of survival without major morbidity are higher among extremely low gestation neonates (ELGANs) born to mothers with chronic hypertension (cHTN) or hypertensive disorders of pregnancy (HDP) compared to ELGANs born to mothers without hypertension (HTN).Study designRetrospective study of prospectively collected data from the Eunice Kennedy Shriver National Institute of Child Health and Human Development Neonatal Research Network. Included children had a birthweight of 401–1000 g and/or gestational age of 220/7 to 286/7 wks. The primary outcome was survival to discharge without major morbidity. Multivariable regression models were used to compare outcomes among ELGANs born to women with cHTN, HDP, and no HTN.ResultsSurvival without morbidities for newborns of mothers with no HTN, cHTN and HDP (29.1%, 32.9%, 37.0% respectively) did not differ after adjustment.ConclusionAfter adjusting for contributing variables maternal HTN is not associated with improved survival free of morbidity among ELGANs.Trials Registration: clinicaltrials.gov Identifier: NCT00063063 (generic database)

ObjectiveTo determine the association of persistent pulmonary hypertension of the newborn (PPHN) with death or disability among infants with moderate or severe hypoxic ischemic encephalopathy (HIE) treated with therapeutic hypothermia.MethodsWe compared infants with and without PPHN enrolled in the hypothermia arm from three randomized controlled trials (RCTs): Induced Hypothermia trial, “usual care” arm of Optimizing Cooling trial, and Late Hypothermia trial. Primary outcome was death or disability at 18–22 months adjusted for severity of HIE, center, and RCT.ResultsAmong 280 infants, 67 (24%) were diagnosed with PPHN. Among infants with and without PPHN, death or disability was 47% vs. 29% (adjusted OR: 1.65, 0.86–3.14) and death was 26% vs. 12% (adjusted OR: 2.04, 0.92–4.53), respectively.ConclusionsPPHN in infants with moderate or severe HIE was not associated with a statistically significant increase in primary outcome. These results should be interpreted with caution given the limited sample size.